Cargando…

Automatic extraction of cell nuclei from H&E-stained histopathological images

Extraction of cell nuclei from hematoxylin and eosin (H&E)-stained histopathological images is an essential preprocessing step in computerized image analysis for disease detection, diagnosis, and prognosis. We present an automated cell nuclei segmentation approach that works with H&E-stained...

Descripción completa

Detalles Bibliográficos
Autores principales: Yi, Faliu, Huang, Junzhou, Yang, Lin, Xie, Yang, Xiao, Guanghua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Society of Photo-Optical Instrumentation Engineers 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5478972/
https://www.ncbi.nlm.nih.gov/pubmed/28653017
http://dx.doi.org/10.1117/1.JMI.4.2.027502
_version_ 1783245053798383616
author Yi, Faliu
Huang, Junzhou
Yang, Lin
Xie, Yang
Xiao, Guanghua
author_facet Yi, Faliu
Huang, Junzhou
Yang, Lin
Xie, Yang
Xiao, Guanghua
author_sort Yi, Faliu
collection PubMed
description Extraction of cell nuclei from hematoxylin and eosin (H&E)-stained histopathological images is an essential preprocessing step in computerized image analysis for disease detection, diagnosis, and prognosis. We present an automated cell nuclei segmentation approach that works with H&E-stained images. A color deconvolution algorithm was first applied to the image to get the hematoxylin channel. Using a morphological operation and thresholding technique on the hematoxylin channel image, candidate target nuclei and background regions were detected, which were then used as markers for a marker-controlled watershed transform segmentation algorithm. Moreover, postprocessing was conducted to split the touching nuclei. For each segmented region from the previous steps, the regional maximum value positions were identified as potential nuclei centers. These maximum values were further grouped into [Formula: see text]-clusters, and the locations within each cluster were connected with the minimum spanning tree technique. Then, these connected positions were utilized as new markers for a watershed segmentation approach. The final number of nuclei at each region was determined by minimizing an objective function that iterated all of the possible [Formula: see text]-values. The proposed method was applied to the pathological images of the tumor tissues from The Cancer Genome Atlas study. Experimental results show that the proposed method can lead to promising results in terms of segmentation accuracy and separation of touching nuclei.
format Online
Article
Text
id pubmed-5478972
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Society of Photo-Optical Instrumentation Engineers
record_format MEDLINE/PubMed
spelling pubmed-54789722018-06-21 Automatic extraction of cell nuclei from H&E-stained histopathological images Yi, Faliu Huang, Junzhou Yang, Lin Xie, Yang Xiao, Guanghua J Med Imaging (Bellingham) Digital Pathology Extraction of cell nuclei from hematoxylin and eosin (H&E)-stained histopathological images is an essential preprocessing step in computerized image analysis for disease detection, diagnosis, and prognosis. We present an automated cell nuclei segmentation approach that works with H&E-stained images. A color deconvolution algorithm was first applied to the image to get the hematoxylin channel. Using a morphological operation and thresholding technique on the hematoxylin channel image, candidate target nuclei and background regions were detected, which were then used as markers for a marker-controlled watershed transform segmentation algorithm. Moreover, postprocessing was conducted to split the touching nuclei. For each segmented region from the previous steps, the regional maximum value positions were identified as potential nuclei centers. These maximum values were further grouped into [Formula: see text]-clusters, and the locations within each cluster were connected with the minimum spanning tree technique. Then, these connected positions were utilized as new markers for a watershed segmentation approach. The final number of nuclei at each region was determined by minimizing an objective function that iterated all of the possible [Formula: see text]-values. The proposed method was applied to the pathological images of the tumor tissues from The Cancer Genome Atlas study. Experimental results show that the proposed method can lead to promising results in terms of segmentation accuracy and separation of touching nuclei. Society of Photo-Optical Instrumentation Engineers 2017-06-21 2017-04 /pmc/articles/PMC5478972/ /pubmed/28653017 http://dx.doi.org/10.1117/1.JMI.4.2.027502 Text en © The Authors. https://creativecommons.org/licenses/by/3.0/ Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
spellingShingle Digital Pathology
Yi, Faliu
Huang, Junzhou
Yang, Lin
Xie, Yang
Xiao, Guanghua
Automatic extraction of cell nuclei from H&E-stained histopathological images
title Automatic extraction of cell nuclei from H&E-stained histopathological images
title_full Automatic extraction of cell nuclei from H&E-stained histopathological images
title_fullStr Automatic extraction of cell nuclei from H&E-stained histopathological images
title_full_unstemmed Automatic extraction of cell nuclei from H&E-stained histopathological images
title_short Automatic extraction of cell nuclei from H&E-stained histopathological images
title_sort automatic extraction of cell nuclei from h&e-stained histopathological images
topic Digital Pathology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5478972/
https://www.ncbi.nlm.nih.gov/pubmed/28653017
http://dx.doi.org/10.1117/1.JMI.4.2.027502
work_keys_str_mv AT yifaliu automaticextractionofcellnucleifromhestainedhistopathologicalimages
AT huangjunzhou automaticextractionofcellnucleifromhestainedhistopathologicalimages
AT yanglin automaticextractionofcellnucleifromhestainedhistopathologicalimages
AT xieyang automaticextractionofcellnucleifromhestainedhistopathologicalimages
AT xiaoguanghua automaticextractionofcellnucleifromhestainedhistopathologicalimages